[{"alternative_title":["ISTA Master's Thesis"],"ddc":["610"],"date_created":"2024-08-02T10:52:40Z","status":"public","file":[{"date_created":"2024-08-14T11:51:24Z","file_name":"Masters_thesis_AriadnaVillanueva.pdf","file_id":"17433","content_type":"application/pdf","file_size":13052436,"access_level":"open_access","date_updated":"2025-02-14T23:30:03Z","creator":"avillanu","relation":"main_file","checksum":"0c2daa174609f0c00919dccc5701d375","embargo":"2025-02-14"},{"checksum":"e9ed4465dfa539ac4c3a8d4d0b6271a1","embargo_to":"open_access","relation":"source_file","creator":"avillanu","access_level":"closed","date_updated":"2025-02-14T23:30:03Z","file_size":45642547,"content_type":"application/zip","file_id":"17434","file_name":"Masters thesis-AriadnaVillanueva.zip","date_created":"2024-08-14T11:51:57Z"}],"OA_place":"publisher","user_id":"ba8df636-2132-11f1-aed0-ed93e2281fdd","year":"2024","day":"13","tmp":{"image":"/images/cc_by_nc_sa.png","short":"CC BY-NC-SA (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)"},"type":"dissertation","publication_status":"published","department":[{"_id":"GradSch"},{"_id":"MaRo"}],"language":[{"iso":"eng"}],"oa":1,"month":"08","date_updated":"2026-04-07T13:03:41Z","license":"https://creativecommons.org/licenses/by-nc-sa/4.0/","corr_author":"1","keyword":["Epigenetics","Multi-omics","Bayesian regression"],"title":"Bayesian linear regression for analyzing general omics data with time-to-event phenotypes","abstract":[{"text":"Recent advancements in molecular diagnostic techniques have enabled the collection of\r\nmultiple types of omics data from patients, including genomics, epigenomics, proteomics,\r\nand transcriptomics. However, we lack effective methods for integrating all these different\r\ndata types and combining them with clinical outcomes to study the molecular mechanisms\r\nthat govern pathological phenotypes. We present multi-omics BayesW, a penalized Bayesian\r\nregression method that can handle general omics data for survival analysis of time-to-event\r\nphenotypes. Our method can: (1) accommodate incomplete data by allowing censored\r\nindividuals, (2) use continuous time-to-event data to test associations of markers with a\r\nphenotype and (3) estimate effects jointly while allowing for independent groups of biological\r\nmarkers. Extensive simulations using planted signals on real data demonstrate that our model\r\naccurately retrieves the true parameters of the model while controlling for false discoveries\r\nand maintaining the expected prediction accuracy. We address data correlations by estimating\r\nthe effects jointly, even between omic groups, while also estimating the individual variance\r\nexplained by each group. We apply our model to two datasets. Using 18,000 individuals from\r\nthe Generation Scotland study we model the association of time at onset of Type 2 Diabetes,\r\nStroke, Ischemic Disease, and Osteoarthritis from baseline study entry, with 831,724 CpG\r\nmethylation probes. We find that large proportions of variation in disease onset times can\r\nbe attributed to methylation as measured in whole blood at baseline in individuals without\r\ndisease symptoms. We then apply our model to The Cancer Genome Atlas (TCGA) pan-cancer\r\ndataset, in which we use 5 types of omics: copy number variation, epigenetics, somatic\r\nmutations, miRNA, and gene expression. For cancer survival age-at-onset we find that, when\r\nfitting the 5 groups together, almost all variation attributable to \"omics\" data is explained by\r\nDNA methylation. When considering progression times, both methylation and gene expression\r\nexplain a large part of the variance. We found 2 genes that are significantly associated (95%\r\nposterior inclusion probability) with cancer survival time, conditional on all other genome-wide\r\nomics data variation. Owing to the vast variability of mechanisms characterizing different\r\ncancers, there are likely few specific genes with a strong signal in a pan-cancer setting. Taken\r\ntogether, we showed the applicability of our multi-omics BayesW model to a wide-range of\r\nbiological questions in multi-omics data.\r\n","lang":"eng"}],"doi":"10.15479/at:ista:17368","has_accepted_license":"1","author":[{"full_name":"Villanueva Marijuan, Ariadna","id":"e0ae4864-133f-11ed-8f02-adaa8dd27540","last_name":"Villanueva Marijuan","first_name":"Ariadna"}],"file_date_updated":"2025-02-14T23:30:03Z","oa_version":"Published Version","supervisor":[{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","last_name":"Robinson","full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","orcid":"0000-0001-8982-8813"}],"page":"60","_id":"17368","citation":{"apa":"Villanueva Marijuan, A. (2024). <i>Bayesian linear regression for analyzing general omics data with time-to-event phenotypes</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/at:ista:17368\">https://doi.org/10.15479/at:ista:17368</a>","ama":"Villanueva Marijuan A. Bayesian linear regression for analyzing general omics data with time-to-event phenotypes. 2024. doi:<a href=\"https://doi.org/10.15479/at:ista:17368\">10.15479/at:ista:17368</a>","ista":"Villanueva Marijuan A. 2024. Bayesian linear regression for analyzing general omics data with time-to-event phenotypes. Institute of Science and Technology Austria.","short":"A. Villanueva Marijuan, Bayesian Linear Regression for Analyzing General Omics Data with Time-to-Event Phenotypes, Institute of Science and Technology Austria, 2024.","ieee":"A. Villanueva Marijuan, “Bayesian linear regression for analyzing general omics data with time-to-event phenotypes,” Institute of Science and Technology Austria, 2024.","chicago":"Villanueva Marijuan, Ariadna. “Bayesian Linear Regression for Analyzing General Omics Data with Time-to-Event Phenotypes.” Institute of Science and Technology Austria, 2024. <a href=\"https://doi.org/10.15479/at:ista:17368\">https://doi.org/10.15479/at:ista:17368</a>.","mla":"Villanueva Marijuan, Ariadna. <i>Bayesian Linear Regression for Analyzing General Omics Data with Time-to-Event Phenotypes</i>. Institute of Science and Technology Austria, 2024, doi:<a href=\"https://doi.org/10.15479/at:ista:17368\">10.15479/at:ista:17368</a>."},"publication_identifier":{"issn":["2791-4585"]},"date_published":"2024-08-13T00:00:00Z","publisher":"Institute of Science and Technology Austria","article_processing_charge":"No","degree_awarded":"MS"}]